Staff Software Engineer, Agentic Infrastructure
Relativity3 months ago
Base Salary
$181k - $271k/yr
Responsibilities
- Own the reliability of agentic infrastructure, including agents, sessions, model routing, context pipelines, inter-agent communication, and supporting services
- Build and maintain infrastructure where off-the-shelf solutions are insufficient
- Deploy and operate local LLM inference across Mac Studio and GPU hardware
- Manage Linux and macOS systems, Proxmox virtual machines and containers, storage, backups, and recovery
- Maintain multi-site networking, including L3 routing, VLANs, DNS, firewalls, and connectivity
- Build CLIs, dashboards, automation, and internal tools for engineering productivity
- Improve observability, debugging, and automated failure recovery
- Contribute upstream to relied-upon open-source projects
- Design practical security for local compute, data handling, and access controls
- Package and deploy portions of the stack into internal and customer environments
- Work directly with engineers to turn recurring problems into improved infrastructure
Requirements
- 7+ years of experience building and operating complex software and compute infrastructure across hardware, operating systems, networking, and automation
- Experience deploying an agentic harness such as OpenClaw, Hermes, SybilClaw, or a comparable system in a real work environment
- Strong Linux and macOS systems experience, including debugging services, processes, storage, permissions, and networking
- Experience operating physical infrastructure, virtual machines, or containers in production
- Strong networking fundamentals, including routing, VLANs, DNS, and firewalls
- Ability to build software, scripts, CLIs, and integrations when existing tools are insufficient
- Meaningful experience contributing to or maintaining open-source software
- Strong judgment around reliability, security, performance, and simplicity
- Experience with ITAR-regulated, air-gapped, export-controlled, or similarly constrained environments is preferred
- Experience operating local LLM inference with Ollama, MLX, vLLM, llama.cpp, or similar is preferred
- Experience with model routing, context management, tool execution, agent state, or multi-agent systems is preferred
- Experience building internal developer infrastructure used daily by engineers is preferred
- Experience deploying systems into customer or forward-deployed environments is preferred
- A GitHub, Gitea, or other body of work demonstrating what the candidate has built is preferred
Benefits
- In-office at least three days per week, with flexibility to work remotely when the work allows
- Competitive salary and equity
- Generous PTO and sick leave policy
- Parental leave
- Annual learning and development stipend
About Relativity
Relativity builds legal data intelligence and e-discovery software used by law firms, corporations, and government agencies to manage litigation, investigations, and regulatory matters. Its flagship product, RelativityOne, is a cloud SaaS platform complemented by on-premises offerings and an extensible app ecosystem, sold via subscriptions and partners. Founded in 2001 (as kCura) and headquartered in Chicago, the company is privately held and received a major private-equity investment in 2021.